DRAMMS

Deformable registration via attribute matching and mutual-saliency weighting

Yangming Ou, Aristeidis Sotiras, Nikos Paragios, Christos Davatzikos

Research output: Contribution to journalArticle

Abstract

A general-purpose deformable registration algorithm referred to as " DRAMMS" is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent of the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences (such as outlier regions). A continuously-valued weighting function named " mutual-saliency" is developed to reflect the matching uniqueness between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.

Original languageEnglish (US)
Pages (from-to)622-639
Number of pages18
JournalMedical Image Analysis
Volume15
Issue number4
DOIs
StatePublished - Aug 2011
Externally publishedYes

Fingerprint

Brain
Experiments
Prostate
Weights and Measures

Keywords

  • Attribute matching
  • Gabor filter bank
  • Image registration
  • Mutual-saliency
  • Outlier data

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology

Cite this

DRAMMS : Deformable registration via attribute matching and mutual-saliency weighting. / Ou, Yangming; Sotiras, Aristeidis; Paragios, Nikos; Davatzikos, Christos.

In: Medical Image Analysis, Vol. 15, No. 4, 08.2011, p. 622-639.

Research output: Contribution to journalArticle

Ou, Yangming ; Sotiras, Aristeidis ; Paragios, Nikos ; Davatzikos, Christos. / DRAMMS : Deformable registration via attribute matching and mutual-saliency weighting. In: Medical Image Analysis. 2011 ; Vol. 15, No. 4. pp. 622-639.
@article{590d68df0cd74d389849c9e49d4b8964,
title = "DRAMMS: Deformable registration via attribute matching and mutual-saliency weighting",
abstract = "A general-purpose deformable registration algorithm referred to as {"} DRAMMS{"} is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent of the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences (such as outlier regions). A continuously-valued weighting function named {"} mutual-saliency{"} is developed to reflect the matching uniqueness between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.",
keywords = "Attribute matching, Gabor filter bank, Image registration, Mutual-saliency, Outlier data",
author = "Yangming Ou and Aristeidis Sotiras and Nikos Paragios and Christos Davatzikos",
year = "2011",
month = "8",
doi = "10.1016/j.media.2010.07.002",
language = "English (US)",
volume = "15",
pages = "622--639",
journal = "Medical Image Analysis",
issn = "1361-8415",
publisher = "Elsevier",
number = "4",

}

TY - JOUR

T1 - DRAMMS

T2 - Deformable registration via attribute matching and mutual-saliency weighting

AU - Ou, Yangming

AU - Sotiras, Aristeidis

AU - Paragios, Nikos

AU - Davatzikos, Christos

PY - 2011/8

Y1 - 2011/8

N2 - A general-purpose deformable registration algorithm referred to as " DRAMMS" is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent of the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences (such as outlier regions). A continuously-valued weighting function named " mutual-saliency" is developed to reflect the matching uniqueness between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.

AB - A general-purpose deformable registration algorithm referred to as " DRAMMS" is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent of the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences (such as outlier regions). A continuously-valued weighting function named " mutual-saliency" is developed to reflect the matching uniqueness between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.

KW - Attribute matching

KW - Gabor filter bank

KW - Image registration

KW - Mutual-saliency

KW - Outlier data

UR - http://www.scopus.com/inward/record.url?scp=78951494198&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78951494198&partnerID=8YFLogxK

U2 - 10.1016/j.media.2010.07.002

DO - 10.1016/j.media.2010.07.002

M3 - Article

VL - 15

SP - 622

EP - 639

JO - Medical Image Analysis

JF - Medical Image Analysis

SN - 1361-8415

IS - 4

ER -